© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 42692
    Prev
    Next
    INDEX
    Explanations

    single-digit numbers

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens—years, percentages, counts, and other numbers—highlighting where concrete figures appear.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     هدف
    -0.07
     Yosh
    -0.07
     хочу
    -0.06
     organised
    -0.06
     mundane
    -0.06
    شد
    -0.06
    Cascade
    -0.06
     publicKey
    -0.06
    :"-
    -0.06
     Favorite
    -0.06
    POSITIVE LOGITS
    -TV
    0.07
    κρα
    0.06
    _Build
    0.06
    urous
    0.06
    OWN
    0.06
    ész
    0.06
    uální
    0.06
    _AC
    0.06
     pleased
    0.06
     billionaire
    0.06
    Activations Density 0.022%

    No Known Activations